update

crawler_sys/site_crawler_by_redis/crawler_xiaohongshu.py

@@ -178,6 +178,7 @@ class Crawler_xiaohongshu():
                     page_data = self.get_one_page_xiaochengxu(page_id, proxies=proxies_num)
                     page_data['release_time'] = int(time_ts*1e3)
                     page_data['platform'] = 'xiaohongshu'
+                    page_data['doc_id'] = page_id
                     # print(page_data)
                     # rds.hset("xiaohongshu", key=page_id, value=json.dumps(page_data))
                     yield page_data